activity
20242026
most citedAggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP

1 citations · 1 across the 7 of their papers we have counts for

collaborators

9 papers

cs.CL2026

Optimal Splitting of Language Models from Mixtures to Specialized Domains

Skyler Seto, Pierre Ablin, Anastasiia Filippova +4

Language models achieve impressive performance on a variety of knowledge, language, and reasoning tasks due to the scale and diversity of pretraining data available. The standard t…

cs.SD2026

Which Data Matter? Embedding-Based Data Selection for Speech Recognition

Zakaria Aldeneh, Skyler Seto, Maureen de Seyssel +8

Modern ASR systems are typically trained on large-scale pseudo-labeled, in-the-wild data spanning multiple domains. While such heterogeneous data benefit generalist models designed…

cs.CL2025

Analyzing Dialectical Biases in LLMs for Knowledge and Reasoning Benchmarks

Eileen Pan, Anna Seo Gyeong Choi, Maartje ter Hoeve +2

Large language models (LLMs) are ubiquitous in modern day natural language processing. However, previous work has shown degraded LLM performance for under-represented English diale…

cs.CL2025

Assessing the Role of Data Quality in Training Bilingual Language Models

Skyler Seto, Maartje ter Hoeve, Maureen de Seyssel +1

Bilingual and multilingual language models offer a promising path toward scaling NLP systems across diverse languages and users. However, their performance often varies wildly betw…

cs.CL2025

Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks

Maureen de Seyssel, Jie Chi, Skyler Seto +3

We introduce a set of training-free ABX-style discrimination tasks to evaluate how multilingual language models represent language identity (form) and semantic content (meaning). I…

cs.LG2025

Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging

Pierre Ablin, Angelos Katharopoulos, Skyler Seto +1

Machine learning models are routinely trained on a mixture of different data domains. Different domain weights yield very different downstream performances. We propose the Soup-of-…